Beyond traditional emission-line diagnostics: Using autoencoders to uncover active galactic nuclei in DESI spectra
Year: 2026
Type: article
Abstract: Context. The growing volume of spectroscopic data in modern surveys motivates the development of data-driven approaches that complement traditional emission-line diagnostics for the identification of active galactic nuclei (AGNs). Aims. We develop and validate a machine-learning (ML) framework for galaxy and AGN classification that exploits the full optical spectrum, using unsupervised learning to capture spectral features within a semi-supervised classification framework that complements classical approaches. Methods. We adapted the SPENDER autoencoder architecture to compress galaxy spectra obtained with the Dark Energy Spectroscopic Instrument (DESI) into a low-dimensional latent space that encodes physically meaningful label-agnostic information. We introduced a quantitative classification method via a k-d tree nearest-neighbor search in latent space. The model was trained on 50 222 spectra from the DESI main survey, corresponding to the internal Guadalupe dataset, released as part of data release 1 (DR1), and restricted to z ≤ 0.5. We validated the performance using labels derived from the FastSpecFit emission line measurements defining seven galaxy classes: AGN, broad-line (BL), composite, star-forming, passive, retired, and other. Results. The model achieves a high performance in identifying AGN and BL sources, with accuracies of 0.952 and 0.965, respectively. The model reliably recovers AGN and BL sources even in spectra with a low signal-to-noise ratio and identifies AGNs missed by single-diagnostic standard methods. Our classification metrics are benchmarked against traditional diagnostics, and we show that they represent lower limits of the true model performance. The latent space learned by the autoencoder not only separates AGN and non-AGN galaxies, but also correlates with key physical properties such as stellar mass and star formation rate, demonstrating that the method captures astrophysical meaningful features. Conclusions. This work demonstrates that unsupervised spectral representation learning implemented within a semi-supervised classification framework offers a powerful and scalable pathway toward more complete and reliable AGN catalogs for current and upcoming large spectroscopic surveys.
Source: Astronomy and Astrophysics
Authors: J. A. Alcolea, M. Siudek, M. Eriksen, M. Mezcua, R. Pucha, S. Juneau, S. Gontcho A Gontcho, S. Panda, J. Aguilar, S. Ahlen, D. Bianchi, A. Brodzeller, D. Brooks, F. J. Castander, T. Claybaugh, A. Cuceu, A. de la Macorra, B. Dey, P. Doel, S. Ferraro, A. Font-Ribera, J. E. Forero-Romero, E. Gaztañaga, G. Gutierrez, C. Hahn, H. K. Herrera-Alcantar, R. Joyce, R. Kehoe, D. Kirkby, T. Kisner, A. Kremin, O. Lahav, C. Lamman, M. Landriau, L. Le Guillou, A. Meisner, R. Miquel, J. Moustakas, S. Nadathur, W. Percival, F. Prada, I. Pérez-Ràfols, G. Rossi, E. Sanchez, E. Schlafly, D. Schlegel, M. Schubnell, J. Silber, D. Sprayberry, G. Tarlé, B. A. Weaver, H. Zou
Institutions: Institute of Space Sciences, Universidad de La Laguna, Instituto de Astrofísica de Canarias, Institute for High Energy Physics, Barcelona Institute of Science and Technology, Port d'Informació Científica, Institut d'Estudis Espacials de Catalunya, University of Arizona, University of Utah, NSF NOIRLab, University of Virginia, International Gemini Observatory, Lawrence Berkeley National Laboratory, Boston University, University of Milan, Brera Astronomical Observatory, National Institute for Astrophysics, University College London, Universidad Nacional Autónoma de México, University of Pittsburgh, University of Toronto, University of California, Berkeley, Institució Catalana de Recerca i Estudis Avançats, Universidad de Los Andes, Universidad de Los Andes, Universidad de Los Andes, University of Portsmouth, Fermi National Accelerator Laboratory, The University of Texas at Austin, Commissariat à l'Énergie Atomique et aux Énergies Alternatives, Université Paris-Saclay, CEA Paris-Saclay - Etablissement de Saclay, Institut d'Astrophysique de Paris, Institut de Recherche sur les Lois Fondamentales de l'Univers, Southern Methodist University, The Ohio State University, Centre National de la Recherche Scientifique, Sorbonne Université, Laboratoire de Physique Nucléaire et de Hautes Énergies, Institut National de Physique Nucléaire et de Physique des Particules, University of Siena, University of Waterloo, Perimeter Institute, Consejo Superior de Investigaciones Científicas, Instituto de Astrofísica de Andalucía, Universitat Politècnica de Catalunya, Sejong University, Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas, Space Telescope Science Institute, University of Michigan, Chinese Academy of Sciences, National Astronomical Observatories
Language: English
Subfield: Astronomy and Astrophysics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,865
Funders: National Science Foundation, U.S. Department of Energy, Gordon and Betty Moore Foundation, Ministerio de Ciencia, Innovación y Universidades, National Energy Research Scientific Computing Center, European Commission, Ministerio de Ciencia e Innovación, Commissariat à l'Énergie Atomique et aux Énergies Alternatives, Narodowa Agencja Wymiany Akademickiej, Office of Science, Science and Technology Facilities Council, Agencia Estatal de Investigación, Division of Astronomical Sciences
Awards: G1044631029, G1105844351, G1175115578, G122673668, G1286236842, G1401168639, COFUND BIST POSTDOCTORAL FELLOWSHIP PROGRAMME, G1590639034, G1813527838, G1855990336, G1863003419, G2133506196, G2262748287, G2309174360, G24120701, G252646220, G2601397997, G2660406951, G294895050, G300979063, G3083819904, G3439265645, G3452655474, G3480869486, G3518538256, G3681454997, G3715634343, G385770566, G4042783231, G419881185, G425668148, G42916606, G430777504, G4501827968, G464105488, G4655338613, G490073602, G491712853, G498139845, G5080475149, G5195188938, G5229162079, G526230902, G5421974903, G5574260043, G5635532810, G593054264, G617610489, G6425459835, G6652958823, G6728930308, G6876926712, G7084143925, G7131467636, Management and Operations of the National Optical Astronomy Observatory, G7395345766, G7434936867, G7805626310, G7863371703, G8174589788, G8345352404, G8399547696, G8497050386, G8575141037, G8667377315, G969889393, G99296377
OpenAlex ID: W7172403427